Elevator safety control system

Abstract

The invention discloses an elevator safety control system, which relates to the technical field of elevator safety. The detection end detects key parameters of an object being transported by the elevator during transportation, and transmits the key parameters of the object to an identification end. The control end detects whether a tire is present in the elevator, and then determines whether the tire is not a bicycle or other vehicle that can enter the elevator according to the width of the tire, and automatically sends an existence signal when the detection is made. The number and weight of people entering the elevator are then analyzed simultaneously, and it is automatically detected whether a weight that should not appear is present, thereby generating two existence signals according to the identification result, and accurately determining whether an electric vehicle is present in the elevator according to the existence signal and the two existence signals. The invention is simple, effective, and easy to use.

Description

Technical Field

[0001] The invention belongs to the technical field of elevator safety control, in particular to an elevator safety control system. Background Art

[0002] Publication number CN107108156A provides an elevator safety control device and an elevator safety control method. When an abnormality of the elevator is detected based on a monitoring signal from a switch or sensor that monitors the elevator status (safety-related switches and sensors, external safety control devices), a nearest floor stop instruction is output to the operation control device so that the car stops at the nearest floor. In the safety control device that performs safety control to stop the car within the time limit of a timer provided in the safety control device, the timer is set to a dual system and has the function of diagnosing the health of the timer itself by comparing the count values ​​of the timers of the dual systems with each other.

[0003] As far as elevator safety is concerned, electric vehicles entering the elevator is a potential safety hazard that cannot be ignored. How to detect the electric vehicles entering the elevator is a problem. Based on this, a solution is provided. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an elevator safety control system, comprising:

[0005] The detection end is used to detect the key parameters of the transport object transported by the elevator during transportation, and transmit the key parameters of the transport object to the identification end;

[0006] The identification end is used to perform existence analysis on key parameters, obtain a real-time value based on the existence analysis, compare the real-time value with the inertia value, and generate a relevant signal when the real-time value is greater than the inertia value. The identification end is used to control the execution unit to prohibit closing the elevator door based on the relevant signal. At this time, the elevator does not run, and the execution unit will play the voice "Electric vehicles are not allowed to enter" until no existence signal is detected.

[0007] Furthermore, the transport object refers to the tire identified from all the real-life photos in the elevator, and the real-time width of the tire is automatically obtained, and the real-time width is compared with the inertia value. When the real-time width exceeds the inertia value, a presence signal is generated; when an even number of presence signals is generated, an alarm signal is automatically generated;

[0008] When the recognition end generates an alarm signal, it automatically notifies the execution unit to prohibit closing the elevator door. At this time, the elevator does not run. At the same time, the execution unit will play the voice "Electric vehicles are prohibited from entering" until no signal is detected.

[0009] Furthermore, the real-time width of the tire is obtained by:

[0010] The detection unit is used to mark the mark to be identified containing the tire and transmit it to the recognition end, and the recognition end receives the mark to be identified with the tire transmitted by the detection unit;

[0011] Obtain the marked tire to be identified, automatically obtain the number of pixels occupied by the widest part of the tire, and then multiply it by the conversion ratio to obtain the real-time width of the tire;

[0012] The conversion ratio is obtained as follows:

[0013] Specify an object of a set length, and then set the corresponding camera to the same angle and parameter ratio installed in the elevator;

[0014] After photographing the corresponding object, obtain the number of pixels it occupies in the length direction, mark it as the occupied number, and then divide the set length by the occupied number, and mark the resulting value as the conversion ratio;

[0015] Get the width of the tire and mark it as the real-time width.

[0016] Furthermore, the inertia value is obtained by:

[0017] Obtain several tires whose tire widths are obtained in the same way and are confirmed to belong to electric vehicles, and mark their tire widths as confirmed widths; obtain all confirmed widths and mark them as Ki, where i=1, ..., n, indicating that there are n confirmed width data;

[0018] Then the mean value P of Ki is automatically calculated, and then the aggregate value W of Ki is calculated using the formula:

[0019] ;

[0020] When W exceeds X1, X1 is the preset value, and Ki is automatically sorted in descending order according to |Ki-P|. Ki is selected in sequence. Each time a Ki is selected, it is automatically deleted. After deletion, the W value is recalculated. If it still exceeds X1, Ki is continued to be selected in sequence for deletion until the W value does not exceed X1. Then the minimum value of the remaining Ki values ​​is marked as the inertia value.

[0021] Furthermore, it also includes:

[0022] The auxiliary detection unit is used to obtain the number of people in the elevator and mark it as the number of people present, and then obtain the total weight in the elevator and mark it as the total weight present;

[0023] The value obtained by dividing the total weight present by the number present is marked as the deemed average weight;

[0024] The auxiliary detection unit is used to transmit the deemed average weight to the recognition end, and the recognition end is used to perform existence determination based on the deemed average weight. The specific method of existence determination is:

[0025] The deemed average weight is compared with the standard upper weight value. When the deemed average weight exceeds the standard upper weight value, a second storage signal is generated. When the second storage signal is generated, the administrator is automatically reminded to check the elevator monitoring. If the administrator issues a prohibition signal, the execution unit is automatically used to prohibit the closing of the elevator door. At this time, the elevator does not run until no existence signal is detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter."

[0026] Furthermore, it also includes an auxiliary detection unit, which is used to obtain the number of people in the elevator and mark it as the number of people present, and then obtain the total weight in the elevator and mark it as the total weight present;

[0027] The value obtained by dividing the total weight present by the number present is marked as the deemed average weight;

[0028] The auxiliary detection unit is used to transmit the deemed average weight to the recognition end, and the recognition end is used to perform existence determination based on the deemed average weight. The specific method of existence determination is:

[0029] The deemed average weight is compared with the standard upper weight value. When the deemed average weight exceeds the standard upper weight value, a two-presence signal is generated. At this time, the recognition end does not generate an alarm signal when an even number of presence signals are generated, but generates a prohibition signal when a presence signal and a two-presence signal are generated;

[0030] At this time, the execution unit automatically prohibits the elevator door from closing. The elevator will not run until no signal is detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter."

[0031] Furthermore, if the identification end only detects either the existence signal or the second storage signal, it will automatically remind the administrator to check the elevator monitoring. If the administrator issues a prohibition signal, the execution unit will automatically prohibit the closing of the elevator door. At this time, the elevator will not run until the existence signal is no longer detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter."

[0032] Furthermore, the standard weight value is obtained by the identification end in the following manner:

[0033] Obtain the number of people and the total weight of the elevator when it is confirmed that there are only people in the elevator, and then divide the total weight by the number of people to obtain the standard weight Zj, where j=1, ..., m, indicating that there are m standard weights;

[0034] Then the mean value P of Zj is automatically calculated, and the aggregate value Q of Zj is calculated using the formula:

[0035] ;

[0036] When Q exceeds X2, Zj is sorted in descending order according to |Zj-P|, and Zj is selected in sequence. Each time a Zj is selected, it is automatically deleted, and the Q value is recalculated after deletion. If it still exceeds X2, Zj is continuously selected in sequence and deleted until the Q value does not exceed X2. Then the maximum value of the remaining Zj values ​​is marked as the standard upper value; X2 is the preset value;

[0037] Here, if the value of the number of deleted Zj divided by m exceeds X3, the maximum value of the undeleted Zj is marked as the standard upper value, and X3 is the preset value.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention detects key parameters of the transport object transported by the elevator through the detection end, and transmits the key parameters of the transport object to the identification end; detects whether there is a tire in the elevator, and then determines whether it is not a bicycle or other vehicles that can enter the elevator according to the width of the tire, and automatically sends an existence signal when it is detected;

[0040] Then, the number and weight of people entering the elevator are analyzed simultaneously, and whether there is weight that should not appear is automatically detected, so that two storage signals are generated according to the recognition results, and whether there is an electric car in the elevator is accurately determined according to the existence signal and the two storage signals; the present invention is simple, effective, and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system block diagram of the elevator safety control system of the present invention;

[0042] Figure 2 It is a system block diagram of the elevator safety control system of the present invention. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 , the present application provides an elevator safety control system, including a detection unit, an identification terminal and an execution unit;

[0045] Among them, the detection unit is used to detect whether there is an electric vehicle entering the elevator. The specific method here is:

[0046] After the elevator door is opened and then closed, all real-life photos in the elevator are obtained through the camera at a set frequency, and are marked as targets to be identified. Whether there is a tire among the targets to be identified is identified. Tire identification is an existing technology, and only one feasible method is given here, specifically:

[0047] Use the trained recognition model to identify tires;

[0048] There are several existing methods for identifying tires. Of course, for the sake of completeness, the specific methods are briefly described below:

[0049] Image acquisition: collect a dataset of images containing tires; these images should cover tires of different types of electric vehicles, and be taken several times against various elevator backgrounds;

[0050] Labeling: labeling the tire in the image, including the tire's location, outline, and any important feature points; this step is usually completed with the help of labeling tools such as LabelImg or CVAT;

[0051] Preprocessing: normalizing, resizing, and enhancing (such as rotating, flipping, and scaling) image data to improve the generalization ability of the model;

[0052] Choose a basic network. Choose a suitable CNN architecture as the basic network, such as AlexNet, VGG, ResNet, etc. These networks have proven their effectiveness in different visual recognition tasks.

[0053] Adjust the structure. According to the specific requirements of tire recognition, it may be necessary to make some adjustments to the basic network, such as increasing or decreasing the number of layers, changing the size of the convolution kernel, etc., to adapt to the characteristics of the tire;

[0054] Training: Use the labeled tire image dataset to train the CNN model. During the training process, the model parameters are continuously optimized through the back propagation algorithm.

[0055] Validation: Evaluate the performance of the model on an independent validation set, focusing on metrics such as accuracy, recall, and F1 score;

[0056] Hyperparameter adjustment: adjust hyperparameters such as learning rate, batch size, and number of iterations based on the verification results to obtain the best performance; that is, the recognition accuracy exceeds the set ratio;

[0057] The detection unit is used to mark the to-be-identified mark containing the tire and transmit it to the recognition end. The recognition end receives the to-be-identified mark with the tire transmitted by the detection unit and performs existence analysis. The specific method of existence analysis is:

[0058] After obtaining the marked tire to be identified, the number of pixels occupied by the widest part of the tire is automatically obtained, and then multiplied by the conversion ratio to obtain the real-time width of the tire; the conversion ratio here is obtained in the following way:

[0059] Specify an object of a set length, and then set the corresponding camera to the same angle and parameter ratio installed in the elevator. The parameters refer to the same clarity and focal length.

[0060] After photographing the corresponding object, obtain the number of pixels it occupies in the length direction, mark it as the occupied number, and then divide the set length by the occupied number, and mark the resulting value as the conversion ratio;

[0061] Get the width of the tire and mark it as the real-time width;

[0062] Compare the real-time width with the inertia value, and generate a presence signal when the real-time width exceeds the inertia value;

[0063] When an even number of presence signals are generated, an alarm signal is automatically generated;

[0064] The inertia value is obtained as follows:

[0065] Obtain several tires whose tire widths are obtained in the same way and are confirmed to belong to electric vehicles, and mark their tire widths as confirmed widths; obtain all confirmed widths and mark them as Ki, where i=1, ..., n, indicating that there are n confirmed width data;

[0066] Then the mean value P of Ki is automatically calculated, and then the aggregate value W of Ki is calculated using the formula:

[0067] ;

[0068] When W exceeds X1, X1 is the preset value, and Ki is automatically sorted in descending order according to |Ki-P|, and Ki is selected in sequence. Each time a Ki is selected, it is automatically deleted, and the W value is recalculated after deletion. If it still exceeds X1, Ki is continuously selected in sequence and deleted until the W value does not exceed X1, and then the smallest value among the remaining Ki values ​​is marked as the inertia value;

[0069] When the recognition end generates an alarm signal, it automatically notifies the execution unit to prohibit closing the elevator door. At this time, the elevator does not run. At the same time, the execution unit will play the voice "Electric vehicles are prohibited from entering" until no signal is detected.

[0070] like Figure 2 As shown, as the second embodiment of the present application, this embodiment provides an elevator safety control system, which specifically includes an auxiliary detection unit, an identification terminal and an execution unit;

[0071] The auxiliary detection unit is used to obtain the number of people in the elevator. The number of people is obtained by the existing technology, which is not the focus of this application, so it is not described in detail here. It is marked as the number of people, and then the total weight in the elevator is obtained, which is marked as the total weight of the existence;

[0072] The total weight of the existence is divided by the number of existences to obtain a numerical value marked as the deemed average weight; the auxiliary detection unit is used to transmit the deemed average weight to the recognition end, and the recognition end is used to perform existence determination based on the deemed average weight. The specific method of existence determination is:

[0073] The deemed average weight is compared with the standard upper weight value, and when the deemed average weight exceeds the standard upper weight value, a second storage signal is generated;

[0074] Here, the standard weight value is obtained by the identification end in the following way:

[0075] Obtain the number of people and the total weight of the elevator when it is confirmed that there are only people in the elevator, and then divide the total weight by the number of people to obtain the standard weight Zj, where j=1, ..., m, indicating that there are m standard weights;

[0076] Then the mean value P of Zj is automatically calculated, and the aggregate value Q of Zj is calculated using the formula:

[0077] ;

[0078] When Q exceeds X2, Zj is sorted in descending order according to |Zj-P|, and Zj is selected in sequence. Each time a Zj is selected, it is automatically deleted, and the Q value is recalculated after deletion. If it still exceeds X2, Zj is continuously selected in sequence and deleted until the Q value does not exceed X2. Then the maximum value of the remaining Zj values ​​is marked as the standard upper value; X2 is the preset value;

[0079] Here, if the value of the number of deleted Zj divided by m exceeds X3, the maximum value of the undeleted Zj is marked as the standard upper value. X3 is a preset value, which is generally 30%;

[0080] When the second existence signal is generated, the administrator is automatically reminded to check the elevator monitoring. If the administrator sends a prohibition signal, the execution unit will automatically prohibit the closing of the elevator door. At this time, the elevator will not run until the existence signal is no longer detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter."

[0081] As the third embodiment of the present application, the present application adopts the verification method of the first embodiment and the second embodiment in combination. The identification end in the present embodiment is used to generate a prohibition signal when the presence signal and the second storage signal are generated. At this time, the elevator door is automatically prohibited from closing through the execution unit. At this time, the elevator does not run until the presence signal is not detected. At the same time, the execution unit will play the voice "Electric vehicles are prohibited from entering";

[0082] If the identification end only detects either the existence signal or the second storage signal, it will automatically remind the administrator to check the elevator monitoring. If the administrator sends a prohibition signal, the execution unit will automatically prohibit the closing of the elevator door. At this time, the elevator will not run until the existence signal is no longer detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter."

[0083] If the identification end does not detect the existence signal and the second storage signal, no processing is performed.

[0084] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0085] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An elevator safety control system, characterized in that: include: The detection end is used to detect the key parameters of the transport object transported by the elevator during transportation, and transmit the key parameters of the transport object to the identification end; The identification end is used to perform existence analysis on key parameters, obtain a real-time value based on the existence analysis, compare the real-time value with the inertia value, and generate a relevant signal when the real-time value is greater than the inertia value. The identification end is used to control the execution unit to prohibit closing the elevator door according to the relevant signal. At this time, the elevator does not run, and the execution unit will play the voice "Electric vehicles are not allowed to enter" until the existence signal is no longer detected; The transport object refers to the tire identified from all the real-life photos in the elevator, and the real-time width of the tire is automatically obtained. The real-time width is compared with the inertia value. When the real-time width exceeds the inertia value, an existence signal is generated; when an even number of existence signals are generated, an alarm signal is automatically generated; When the recognition end generates an alarm signal, it automatically notifies the execution unit to prohibit closing the elevator door. At this time, the elevator does not run, and the execution unit will play a voice message "Electric vehicles are prohibited from entering" until no signal is detected; The inertia value is obtained by: Obtain several tires whose tire widths are obtained in the same way and are confirmed to belong to electric vehicles, and mark their tire widths as confirmed widths; obtain all confirmed widths and mark them as Ki, where i=1, ..., n, indicating that there are n confirmed width data; Then the mean value P of Ki is automatically calculated, and then the aggregate value W of Ki is calculated using the formula: When W exceeds X1, X1 is the preset value, and Ki is automatically sorted in descending order according to |Ki-P|. Ki is selected in sequence. Each time a Ki is selected, it is automatically deleted. After deletion, the W value is recalculated. If it still exceeds X1, Ki is continued to be selected in sequence for deletion until the W value does not exceed X1. Then the minimum value of the remaining Ki values ​​is marked as the inertia value.

2. An elevator safety control system according to claim 1, characterized in that: The real-time width of the tire is obtained by: The detection unit is used to mark the mark to be identified containing the tire and transmit it to the recognition end, and the recognition end receives the mark to be identified with the tire transmitted by the detection unit; Obtain the mark to be identified of the marked tire, automatically obtain the number of pixels occupied by the widest part of the tire, and then multiply it by the conversion ratio to obtain the real-time width of the tire; The conversion ratio is obtained as follows: Specify an object of a set length, and then set the corresponding camera to the same angle and parameter ratio installed in the elevator; After photographing the corresponding object, obtain the number of pixels it occupies in the length direction, mark it as the occupied number, and then divide the set length by the occupied number, and mark the resulting value as the conversion ratio; Get the width of the tire and mark it as the real-time width.

3. An elevator safety control system according to claim 1, characterized in that: Also includes: The auxiliary detection unit is used to obtain the number of people in the elevator and mark it as the number of people present, and then obtain the total weight in the elevator and mark it as the total weight present; The value obtained by dividing the total weight present by the number present is marked as the deemed average weight; The auxiliary detection unit is used to transmit the deemed average weight to the recognition end, and the recognition end is used to perform existence determination based on the deemed average weight. The specific method of existence determination is: The deemed average weight is compared with the standard upper weight value. When the deemed average weight exceeds the standard upper weight value, a second storage signal is generated. When the second storage signal is generated, the administrator is automatically reminded to check the elevator monitoring. If the administrator issues a prohibition signal, the execution unit is automatically used to prohibit the closing of the elevator door. At this time, the elevator does not run until no existence signal is detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter." 4. An elevator safety control system according to claim 1, characterized in that: Also includes: The auxiliary detection unit is used to obtain the number of people in the elevator and mark it as the number of people present, and then obtain the total weight in the elevator and mark it as the total weight present; The value obtained by dividing the total weight present by the number present is marked as the deemed average weight; The auxiliary detection unit is used to transmit the deemed average weight to the recognition end, and the recognition end is used to perform existence determination based on the deemed average weight. The specific method of existence determination is: The deemed average weight is compared with the standard upper weight value. When the deemed average weight exceeds the standard upper weight value, a two-presence signal is generated. At this time, the recognition end does not generate an alarm signal when an even number of presence signals are generated, but generates a prohibition signal when a presence signal and a two-presence signal are generated; At this time, the execution unit automatically prohibits the elevator door from closing. The elevator will not run until no signal is detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter".

5. An elevator safety control system according to claim 4, characterized in that: If the identification end only detects either the presence signal or the second storage signal, it will automatically remind the administrator to check the elevator monitoring. If the administrator sends a prohibition signal, the execution unit will automatically prohibit the closing of the elevator door. At this time, the elevator will not run until the presence signal is no longer detected. At the same time, the execution unit will play the voice "Electric vehicles are not allowed to enter." 6. An elevator safety control system according to claim 4 or 5, characterized in that: The standard upper weight value is obtained by the identification end in the following way: The number of people and the total weight of the elevator are obtained when it is confirmed that there are only people in the elevator, and then the total weight is divided by the number of people to obtain the standard weight Zj, where j = 1, ..., m, indicating that there are m standard weights; Then the mean value P of Zj is automatically calculated, and the aggregate value Q of Zj is calculated using the formula: When Q exceeds X2, Zj is sorted in descending order according to |Zj-P|, and Zj is selected in sequence. Each time a Zj is selected, it is automatically deleted, and the Q value is recalculated after deletion. If it still exceeds X2, Zj is continuously selected in sequence and deleted until the Q value does not exceed X2. Then the maximum value of the remaining Zj values ​​is marked as the standard upper value; X2 is the preset value; Here, if the value of the number of deleted Zj divided by m exceeds X3, the maximum value of the undeleted Zj is marked as the standard upper value, and X3 is the preset value.

Images